Research Interests

My scientific background lies in neuroscience, beginning as an undergraduate at Washington University in St. Louis, where I double majored in Biology and Psychology. I then completed a Medical Scientist Training Program at UCLA with a PhD in Neuroscience where I used resting state functional MRI and diffusion tensor imaging to study children with autism spectrum disorders. As part of my diagnostic radiology residency at Penn I completed a T-32 funded postdoctoral research year and an Imaging Informatics Fellowship. My research has shifted towards more translational research, with an emphasis on applying advanced neuroimaging and artificial intelligence methods to diagnoses encountered more frequently in clinical neuroradiology. This includes projects on mesial temporal sclerosis, glioblastoma and multiple sclerosis, as well as developing a system for automated diagnosis of brain MRIs that can augment the performance of radiologists.

My clinical training consisted of a combined MD/PhD at UCLA, radiology residency at the University of Pennsylvania and neuroradiology fellowship at UCSF. My clinical work motivates me to implement the next generation of artificial intelligence technologies for radiology, within neuroimaging in particular.

For a complete list of my publications, see:  Google Scholar and PubMed

I wrote a blog post for the American College of Radiology Data Science Institute on what I consider the major barriers to integrating artificial intelligence methods into radiology practice

I have been quoted in other articles from the ACR and RSNA about the future of artificial intelligence in radiology practice and resident education

Quality improvement project to reduce unnecessary contrast use when imaging of multiple sclerosis patients:

This work, published in Journal of the American College of Radiology received a Radiology Business imaging innovation award as well as the Penn Radiology Resident Quality and Safety Award, and was covered by several news outlets here